--- title: "Deploy Ombre-Brain" description: "Self-hosted emotional memory for AI with Obsidian storage and search." category: "AI/ML" url: https://railway.com/deploy/ombre-brain --- # Deploy Ombre-Brain Self-hosted emotional memory for AI with Obsidian storage and search. **[Deploy Ombre-Brain on Railway](https://railway.com/template/ombre-brain)** - **Creator:** Muhammad Bilal - **Category:** AI/ML - **Total deploys:** 1 ## Template content ### ombre-brain - **Image:** p0luz/ombre-brain:latest - **Public domain:** Yes ## Documentation # Deploy and Host Ombre Brain on Railway Ombre Brain is a memory and knowledge service designed to persist and retrieve information for AI applications. It provides an HTTP-based MCP transport, semantic embedding generation, memory compression and tagging, and persistent storage for Markdown memories, SQLite vector data, configuration, OAuth registrations, and tunnel data. ## About Hosting Ombre Brain Hosting Ombre Brain on Railway involves deploying the `p0luz/ombre-brain:latest` Docker image as a Railway service. The application listens internally on port `8000` and binds to `0.0.0.0` so it can receive Railway network traffic. The service uses the Streamable HTTP MCP transport and requires a persistent Railway Volume mounted at `/app/buckets`. This directory stores memory files, SQLite vector data, configuration, OAuth registrations, and tunnel data. Railway environment variables configure the application port, bind address, transport, persistent directory, configuration path, dashboard password, and API keys used for compression and embeddings. The service runs using Railway's Docker runtime. ## Common Use Cases * Persistent AI memory and knowledge storage * MCP-based AI applications using Streamable HTTP transport * Semantic search and retrieval using persistent vector data ## Dependencies for Ombre Brain Hosting * Ombre Brain Docker image * Persistent Railway Volume * API key for memory compression and tagging * API key for semantic embedding generation ### Deployment Dependencies * [Ombre Brain GitHub Repository](https://github.com/P0luz/Ombre-Brain) * [Ombre Brain Docker Image](https://hub.docker.com/r/p0luz/ombre-brain) ### Implementation Details #### Docker Deploy the following Docker image: ```docker p0luz/ombre-brain:latest ``` Railway uses the Docker runtime for this deployment. No custom build or start commands are required. #### Public Networking The application listens on port `8000`. | Protocol | Proxy Type | Target Port | Purpose | | -------- | ---------- | ----------: | --------------------------------------------- | | HTTP | HTTP Proxy | 8000 | Ombre Brain HTTP, dashboard, and MCP endpoint | The application is configured to bind to all interfaces: ```env HOST=0.0.0.0 ``` After deployment, generate a Railway domain for port `8000` under **Settings → Networking → Generate Domain**. #### Environment Variables Configure the following variables in the Railway service: | Variable | Required | Description | | -------------------------- | -------- | ------------------------------------------------------- | | `OMBRE_PORT` | Yes | Internal HTTP server port used by the Docker deployment | | `OMBRE_BIND_HOST` | Yes | Address the application binds to | | `OMBRE_TRANSPORT` | Yes | Enables the Streamable HTTP MCP transport | | `OMBRE_VAULT_DIR` | Yes | Persistent memory and vault directory | | `OMBRE_CONFIG_PATH` | Yes | Persistent Ombre Brain configuration path | | `OMBRE_DASHBOARD_PASSWORD` | Yes | Password used to log in to the Ombre Brain dashboard | | `OMBRE_COMPRESS_API_KEY` | Yes | API key used for memory compression and tagging | | `OMBRE_EMBED_API_KEY` | Yes | API key used for semantic embedding generation | Raw Editor example: ```env OMBRE_PORT=8000 OMBRE_BIND_HOST=0.0.0.0 OMBRE_TRANSPORT=streamable-http OMBRE_VAULT_DIR=/app/buckets OMBRE_CONFIG_PATH=/app/buckets/config.yaml OMBRE_DASHBOARD_PASSWORD=${{secret(32)}} OMBRE_COMPRESS_API_KEY=${{secret(32)}} OMBRE_EMBED_API_KEY=${{secret(32)}} ``` #### Persistent Storage Persistent storage is required. To add the volume: 1. Open the Ombre Brain service in Railway. 2. Go to **Settings**. 3. Open **Volumes**. 4. Add a volume named `data`. 5. Set the mount path to: ```text /app/buckets ``` The volume is required to persist memory Markdown files, SQLite vector data, configuration, OAuth registrations, and tunnel data across deployments and restarts. #### Build & Start No custom build or start commands are required. Railway deploys the provided Docker image using the Docker runtime. #### Accessing the Application After deployment: 1. Open the Ombre Brain service in Railway. 2. Go to **Settings → Networking**. 3. Generate a Railway domain for port `8000`. 4. Open the generated HTTPS URL in your browser. 5. On your first login, use the value configured for `OMBRE_DASHBOARD_PASSWORD` as the dashboard login password. If you use Railway's `${{secret(32)}}` expression, Railway generates the password value for you. Store or copy the generated value securely if you need to log in again. The deployment documentation does not specify a separate default username or other default credentials. ## Why Deploy Ombre Brain on Railway? Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it. By deploying Ombre Brain on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway. ## Similar templates - [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform. - [stella](https://railway.com/deploy/stella) — Self-host stella with web, API, Postgres, Redis, and object storage. - [Hermes Agent | OpenClaw Alternative with Dashboard](https://railway.com/deploy/hermes-agent-or-openclaw-alternative-wit) — Self-Hosted Hermes AI Agent for Telegram, Discord & Slack Open this page in a browser: https://railway.com/deploy/ombre-brain